{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:29:46Z","timestamp":1759332586293,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302183, 62372191, 62302187"],"award-info":[{"award-number":["62302183, 62372191, 62302187"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1145\/3658644.3690268","type":"proceedings-article","created":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T12:19:20Z","timestamp":1733746760000},"page":"1256-1270","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Membership Inference Attacks against Vision Transformers: Mosaic MixUp Training to the Defense"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8034-2689","authenticated-orcid":false,"given":"Qiankun","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, Hubei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4078-5140","authenticated-orcid":false,"given":"Di","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, Hubei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1100-2233","authenticated-orcid":false,"given":"Boyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, Hubei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5365-904X","authenticated-orcid":false,"given":"Bin","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, Hubei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4825-8153","authenticated-orcid":false,"given":"Bingqian","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, Hubei, China"}]}],"member":"320","published-online":{"date-parts":[[2024,12,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_3_2_1_2_1","volume-title":"Quantifying Attention Flow in Transformers. In Annual Meeting of the Association for Computational Linguistics.","author":"Abnar Samira","year":"2020","unstructured":"Samira Abnar and Willem Zuidema. 2020. Quantifying Attention Flow in Transformers. In Annual Meeting of the Association for Computational Linguistics."},{"key":"e_1_3_2_1_3_1","volume-title":"Efros","author":"Bai Yutong","year":"2023","unstructured":"Yutong Bai, Xinyang Geng, Karttikeya Mangalam, Amir Bar, Alan Yuille, Trevor Darrell, Jitendra Malik, and Alexei A. Efros. 2023. Sequential Modeling Enables Scalable Learning for Large Vision Models."},{"key":"e_1_3_2_1_4_1","volume-title":"Language Models are Few-Shot Learners. ArXiv","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, T. J. Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeff Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. ArXiv, Vol. abs\/2005.14165 (2020)."},{"key":"e_1_3_2_1_5_1","volume-title":"Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation. In ECCV Workshops.","author":"Cao Hu","year":"2021","unstructured":"Hu Cao, Yueyue Wang, Joy Chen, Dongsheng Jiang, Xiaopeng Zhang, Qi Tian, and Manning Wang. 2021. Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation. In ECCV Workshops."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_7_1","volume-title":"Membership Inference Attacks From First Principles. 2022 IEEE Symposium on Security and Privacy (SP) (2022)","author":"Carlini Nicholas","year":"2022","unstructured":"Nicholas Carlini, Steve Chien, Milad Nasr, Shuang Song, A. Terzis, and Florian Tram\u00e8r. 2022. Membership Inference Attacks From First Principles. 2022 IEEE Symposium on Security and Privacy (SP) (2022), 1897--1914."},{"key":"e_1_3_2_1_8_1","volume-title":"Extracting Training Data from Diffusion Models. ArXiv","author":"Carlini Nicholas","year":"2023","unstructured":"Nicholas Carlini, Jamie Hayes, Milad Nasr, Matthew Jagielski, Vikash Sehwag, Florian Tram\u00e8r, Borja Balle, Daphne Ippolito, and Eric Wallace. 2023. Extracting Training Data from Diffusion Models. ArXiv, Vol. abs\/2301.13188 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"RegionViT: Regional-to-Local Attention for Vision Transformers. ArXiv","author":"Chen Chun-Fu","year":"2021","unstructured":"Chun-Fu Chen, Rameswar Panda, and Quanfu Fan. 2021. RegionViT: Regional-to-Local Attention for Vision Transformers. ArXiv, Vol. abs\/2106.02689 (2021)."},{"key":"e_1_3_2_1_10_1","volume-title":"Relaxloss: Defending membership inference attacks without losing utility. arXiv preprint arXiv:2207.05801","author":"Chen Dingfan","year":"2022","unstructured":"Dingfan Chen, Ning Yu, and Mario Fritz. 2022. Relaxloss: Defending membership inference attacks without losing utility. arXiv preprint arXiv:2207.05801 (2022)."},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security","author":"Chen Dingfan","year":"2019","unstructured":"Dingfan Chen, Ning Yu, Yang Zhang, and Mario Fritz. 2019. GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models. Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security (2019)."},{"key":"e_1_3_2_1_12_1","volume-title":"Gridmask data augmentation. arXiv preprint arXiv:2001.04086","author":"Chen Pengguang","year":"2020","unstructured":"Pengguang Chen, Shu Liu, Hengshuang Zhao, and Jiaya Jia. 2020. Gridmask data augmentation. arXiv preprint arXiv:2001.04086 (2020)."},{"key":"e_1_3_2_1_13_1","volume-title":"Label-Only Membership Inference Attacks. ArXiv","author":"Choquette-Choo Christopher A.","year":"2020","unstructured":"Christopher A. Choquette-Choo, Florian Tram\u00e8r, Nicholas Carlini, and Nicolas Papernot. 2020. Label-Only Membership Inference Attacks. ArXiv, Vol. abs\/2007.14321 (2020)."},{"key":"e_1_3_2_1_14_1","volume-title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers. In Neural Information Processing Systems.","author":"Chu Xiangxiang","year":"2021","unstructured":"Xiangxiang Chu, Zhi Tian, Yuqing Wang, Bo Zhang, Haibing Ren, Xiaolin Wei, Huaxia Xia, and Chunhua Shen. 2021. Twins: Revisiting the Design of Spatial Attention in Vision Transformers. In Neural Information Processing Systems."},{"key":"e_1_3_2_1_15_1","volume-title":"Harald Kittler, and Allan C. Halpern.","author":"Codella Noel C. F.","year":"2019","unstructured":"Noel C. F. Codella, Veronica M Rotemberg, Philipp Tschandl, M. E. Celebi, Stephen W. Dusza, David Gutman, Brian Helba, Aadi Kalloo, Konstantinos Liopyris, Michael Armando Marchetti, Harald Kittler, and Allan C. Halpern. 2019. Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC). ArXiv, Vol. abs\/1902.03368 (2019). https:\/\/api.semanticscholar.org\/CorpusID:60440592"},{"key":"e_1_3_2_1_16_1","volume-title":"Cinic-10 is not imagenet or cifar-10. arXiv preprint arXiv:1810.03505","author":"Darlow Luke N","year":"2018","unstructured":"Luke N Darlow, Elliot J Crowley, Antreas Antoniou, and Amos J Storkey. 2018. Cinic-10 is not imagenet or cifar-10. arXiv preprint arXiv:1810.03505 (2018)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_18_1","volume-title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Dong Xiaoyi","year":"2021","unstructured":"Xiaoyi Dong, Jianmin Bao, Dongdong Chen, Weiming Zhang, Nenghai Yu, Lu Yuan, Dong Chen, and Baining Guo. 2021. CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021), 12114--12124."},{"key":"e_1_3_2_1_19_1","volume-title":"International Conference on Learning Representations.","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_20_1","unstructured":"Alaaeldin El-Nouby Hugo Touvron Mathilde Caron Piotr Bojanowski Matthijs Douze Armand Joulin Ivan Laptev Natalia Neverova Gabriel Synnaeve Jakob Verbeek and Herv\u00e9 J\u00e9gou. 2021. XCiT: Cross-Covariance Image Transformers. In Neural Information Processing Systems."},{"key":"e_1_3_2_1_21_1","volume-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021","author":"Fang Jiemin","year":"2021","unstructured":"Jiemin Fang, Lingxi Xie, Xinggang Wang, Xiaopeng Zhang, Wenyu Liu, and Qi Tian. 2021. MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021), 12053--12062."},{"key":"e_1_3_2_1_22_1","volume-title":"Data-efficient Large Vision Models through Sequential Autoregression. arXiv preprint arXiv:2402.04841","author":"Guo Jianyuan","year":"2024","unstructured":"Jianyuan Guo, Zhiwei Hao, Chengcheng Wang, Yehui Tang, Han Wu, Han Hu, Kai Han, and Chang Xu. 2024. Data-efficient Large Vision Models through Sequential Autoregression. arXiv preprint arXiv:2402.04841 (2024)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Kai Han Yunhe Wang Hanting Chen Xinghao Chen Jianyuan Guo Zhenhua Liu Yehui Tang An Xiao Chunjing Xu Yixing Xu et al. 2022. A survey on vision transformer. IEEE transactions on pattern analysis and machine intelligence Vol. 45 1 (2022) 87--110.","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"e_1_3_2_1_24_1","unstructured":"Kai Han An Xiao Enhua Wu Jianyuan Guo Chunjing Xu and Yunhe Wang. 2021. Transformer in Transformer. In Neural Information Processing Systems."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.2478\/popets-2019-0008"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.2478\/popets-2019-0067"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447867"},{"key":"e_1_3_2_1_28_1","volume-title":"Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer. ArXiv","author":"Huang Zilong","year":"2021","unstructured":"Zilong Huang, Youcheng Ben, Guozhong Luo, Pei Cheng, Gang Yu, and Bin Fu. 2021. Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer. ArXiv, Vol. abs\/2106.03650 (2021)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3363201"},{"key":"e_1_3_2_1_30_1","volume-title":"Fahad Shahbaz Khan, and Mubarak Shah.","author":"Khan Salman","year":"2022","unstructured":"Salman Khan, Muzammal Naseer, Munawar Hayat, Syed Waqas Zamir, Fahad Shahbaz Khan, and Mubarak Shah. 2022. Transformers in vision: A survey. ACM computing surveys (CSUR), Vol. 54, 10s (2022), 1--41."},{"key":"e_1_3_2_1_31_1","volume-title":"Xiaoshuang Shi, and Kaidi Xu.","author":"Kong Fei","year":"2023","unstructured":"Fei Kong, Jinhao Duan, Ruipeng Ma, Hengtao Shen, Xiao lan Zhu, Xiaoshuang Shi, and Kaidi Xu. 2023. An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization. ArXiv, Vol. abs\/2305.18355 (2023)."},{"key":"e_1_3_2_1_32_1","unstructured":"Alex Krizhevsky. 2009. Learning Multiple Layers of Features from Tiny Images."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security","author":"Li Zheng","year":"2020","unstructured":"Zheng Li and Yang Zhang. 2020. Membership Leakage in Label-Only Exposures. Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security (2020)."},{"key":"e_1_3_2_1_34_1","volume-title":"CAT: Cross Attention in Vision Transformer. 2022 IEEE International Conference on Multimedia and Expo (ICME)","author":"Lin Hezheng","year":"2021","unstructured":"Hezheng Lin, Xingyi Cheng, Xiangyu Wu, Fan Yang, Dong Shen, Zhongyuan Wang, Qing Song, and Wei Yuan. 2021. CAT: Cross Attention in Vision Transformer. 2022 IEEE International Conference on Multimedia and Expo (ICME) (2021), 1--6."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3484749"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3560684"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_38_1","volume-title":"APRIL: Finding the Achilles' Heel on Privacy for Vision Transformers. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Lu Jiahao","year":"2021","unstructured":"Jiahao Lu, Xi Sheryl Zhang, Tianli Zhao, Xiangyu He, and Jian Cheng. 2021. APRIL: Finding the Achilles' Heel on Privacy for Vision Transformers. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021), 10041--10050."},{"key":"e_1_3_2_1_39_1","volume-title":"2019 IEEE Symposium on Security and Privacy (SP)","author":"Nasr Milad","year":"2018","unstructured":"Milad Nasr, R. Shokri, and Amir Houmansadr. 2018. Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning. 2019 IEEE Symposium on Security and Privacy (SP) (2018), 739--753."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243855"},{"key":"e_1_3_2_1_41_1","volume-title":"White-box Membership Inference Attacks against Diffusion Models. ArXiv","author":"Pang Yan","year":"2023","unstructured":"Yan Pang, Tianhao Wang, Xu Kang, Mengdi Huai, and Yang Zhang. 2023. White-box Membership Inference Attacks against Diffusion Models. ArXiv, Vol. abs\/2308.06405 (2023)."},{"key":"e_1_3_2_1_42_1","volume-title":"Learning Transferable Visual Models From Natural Language Supervision. In International Conference on Machine Learning.","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In International Conference on Machine Learning."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23119"},{"key":"e_1_3_2_1_44_1","volume-title":"ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models. ArXiv","author":"Salem A.","year":"2018","unstructured":"A. Salem, Yang Zhang, Mathias Humbert, Mario Fritz, and Michael Backes. 2018. ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models. ArXiv, Vol. abs\/1806.01246 (2018)."},{"key":"e_1_3_2_1_45_1","volume-title":"Muhammad Haris Khan, Munawar Hayat, Fahad Shahbaz Khan, and Huazhu Fu.","author":"Shamshad Fahad","year":"2023","unstructured":"Fahad Shamshad, Salman Khan, Syed Waqas Zamir, Muhammad Haris Khan, Munawar Hayat, Fahad Shahbaz Khan, and Huazhu Fu. 2023. Transformers in medical imaging: A survey. Medical Image Analysis (2023)."},{"key":"e_1_3_2_1_46_1","volume-title":"Membership Privacy for Machine Learning Models Through Knowledge Transfer. In AAAI Conference on Artificial Intelligence.","author":"Shejwalkar Virat","year":"2021","unstructured":"Virat Shejwalkar and Amir Houmansadr. 2021. Membership Privacy for Machine Learning Models Through Knowledge Transfer. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_47_1","volume-title":"Membership Inference Attacks Against Machine Learning Models. 2017 IEEE Symposium on Security and Privacy (SP)","author":"Shokri R.","year":"2016","unstructured":"R. Shokri, Marco Stronati, Congzheng Song, and Vitaly Shmatikov. 2016. Membership Inference Attacks Against Machine Learning Models. 2017 IEEE Symposium on Security and Privacy (SP) (2016), 3--18."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"e_1_3_2_1_49_1","volume-title":"Systematic Evaluation of Privacy Risks of Machine Learning Models. In USENIX Security Symposium.","author":"Song Liwei","year":"2020","unstructured":"Liwei Song and Prateek Mittal. 2020. Systematic Evaluation of Privacy Risks of Machine Learning Models. In USENIX Security Symposium."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_1_51_1","volume-title":"Rethinking the Inception Architecture for Computer Vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Szegedy Christian","year":"2015","unstructured":"Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, and Zbigniew Wojna. 2015. Rethinking the Inception Architecture for Computer Vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015), 2818--2826."},{"key":"e_1_3_2_1_52_1","volume-title":"International Conference on Machine Learning.","author":"Touvron Hugo","year":"2020","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv'e J'egou. 2020. Training data-efficient image transformers & distillation through attention. In International Conference on Machine Learning."},{"key":"e_1_3_2_1_53_1","volume-title":"LLaMA: Open and Efficient Foundation Language Models. ArXiv","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. ArXiv, Vol. abs\/2302.13971 (2023)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.161"},{"key":"e_1_3_2_1_55_1","volume-title":"Adapting LLaMA Decoder to Vision Transformer. arXiv preprint arXiv:2404.06773","author":"Wang Jiahao","year":"2024","unstructured":"Jiahao Wang, Wenqi Shao, Mengzhao Chen, Chengyue Wu, Yong Liu, Kaipeng Zhang, Songyang Zhang, Kai Chen, and Ping Luo. 2024. Adapting LLaMA Decoder to Vision Transformer. arXiv preprint arXiv:2404.06773 (2024)."},{"key":"e_1_3_2_1_56_1","volume-title":"KVT: k-NN Attention for Boosting Vision Transformers. ArXiv","author":"Wang Pichao","year":"2021","unstructured":"Pichao Wang, Xue Wang, F. Wang, Ming Lin, Shuning Chang, Wen Xie, Hao Li, and Rong Jin. 2021. KVT: k-NN Attention for Boosting Vision Transformers. ArXiv, Vol. abs\/2106.00515 (2021)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598079"},{"key":"e_1_3_2_1_58_1","volume-title":"Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security","author":"Ye Jiayuan","year":"2021","unstructured":"Jiayuan Ye, Aadyaa Maddi, Sasi Kumar Murakonda, and R. Shokri. 2021. Enhanced Membership Inference Attacks against Machine Learning Models. Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security (2021)."},{"key":"e_1_3_2_1_59_1","volume-title":"Cross-Modal Self-Attention Network for Referring Image Segmentation. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Ye Linwei","year":"2019","unstructured":"Linwei Ye, Mrigank Rochan, Zhi Liu, and Yang Wang. 2019. Cross-Modal Self-Attention Network for Referring Image Segmentation. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019), 10494--10503."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"e_1_3_2_1_61_1","volume-title":"International Conference on Learning Representations.","author":"Zhang Hongyi","year":"2018","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, and David Lopez-Paz. 2018. mixup: Beyond Empirical Risk Minimization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.082"},{"key":"e_1_3_2_1_63_1","volume-title":"DeepViT: Towards Deeper Vision Transformer. ArXiv","author":"Zhou Daquan","year":"1886","unstructured":"Daquan Zhou, Bingyi Kang, Xiaojie Jin, Linjie Yang, Xiaochen Lian, Qibin Hou, and Jiashi Feng. 2021. DeepViT: Towards Deeper Vision Transformer. ArXiv, Vol. abs\/2103.11886 (2021)."},{"key":"e_1_3_2_1_64_1","volume-title":"Refiner: Refining Self-attention for Vision Transformers. ArXiv","author":"Zhou Daquan","year":"2021","unstructured":"Daquan Zhou, Yujun Shi, Bingyi Kang, Weihao Yu, Zihang Jiang, Yuan Li, Xiaojie Jin, Qibin Hou, and Jiashi Feng. 2021. Refiner: Refining Self-attention for Vision Transformers. ArXiv, Vol. abs\/2106.03714 (2021)."},{"key":"e_1_3_2_1_65_1","volume-title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection. In International Conference on Learning Representations.","author":"Zhu Xizhou","year":"2021","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2021. Deformable DETR: Deformable Transformers for End-to-End Object Detection. In International Conference on Learning Representations."}],"event":{"name":"CCS '24: ACM SIGSAC Conference on Computer and Communications Security","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"],"location":"Salt Lake City UT USA","acronym":"CCS '24"},"container-title":["Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658644.3690268","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3658644.3690268","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T06:22:22Z","timestamp":1755843742000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658644.3690268"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":65,"alternative-id":["10.1145\/3658644.3690268","10.1145\/3658644"],"URL":"https:\/\/doi.org\/10.1145\/3658644.3690268","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2024-12-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}